Towards Distraction-Robust Active Visual Tracking
This addresses robustness issues in visual tracking for applications like robotics and surveillance, though it is incremental as it builds on existing multi-agent and adversarial learning methods.
The paper tackles the problem of active visual tracking in the presence of distracting objects by proposing a mixed cooperative-competitive multi-agent game, where distractors learn to expose tracker weaknesses, resulting in a tracker that performs distraction-robust tracking and generalizes to unseen environments.
In active visual tracking, it is notoriously difficult when distracting objects appear, as distractors often mislead the tracker by occluding the target or bringing a confusing appearance. To address this issue, we propose a mixed cooperative-competitive multi-agent game, where a target and multiple distractors form a collaborative team to play against a tracker and make it fail to follow. Through learning in our game, diverse distracting behaviors of the distractors naturally emerge, thereby exposing the tracker's weakness, which helps enhance the distraction-robustness of the tracker. For effective learning, we then present a bunch of practical methods, including a reward function for distractors, a cross-modal teacher-student learning strategy, and a recurrent attention mechanism for the tracker. The experimental results show that our tracker performs desired distraction-robust active visual tracking and can be well generalized to unseen environments. We also show that the multi-agent game can be used to adversarially test the robustness of trackers.